International Journal Software Engineering and Computer Science (IJSECS)

Sales Data Clustering Using the K-Means Algorithm to Determine Retail Product Needs

Riwan Irosucipto Manarung, Edy Widodo, Anggi Muhammad Rifai — Tue, 01 Apr 2025 00:00:00 +0700

Sales data is a systematic record of transactional behavior with goods or services distributed over time boundaries and furnishes primary key business metrics for evaluating and planning. Using the K-Means clustering algorithm, this research segments retail product demand by differences attributes to identify demand patterns. The iterative process of clustering ended at the fifth cycle after the division of objects in each cluster stabilized, which can serve as a sign that we arrive at an optimal solution. Results showed that the first cluster located at a centroid 94, 6 contains 100 data items belonging in a primary set and similarly fifth cluster (same centroid) had also same number of products. The automated approach of Collaboratory also differs from the manual method where there are not pre-defined cluster initial values in our preliminary setup. Despite this procedural difference, there is a remarkable concision in the results which demonstrates the strength of the method when implemented using different ingrained constructions. These results offer some refined results on product classification, which is essential to solve the problem that retail ranks may vary during inventory management and sales optimization.

Application of Machine Learning in Computer Networks: Techniques, Datasets, and Applications for Performance and Security Optimization

Memed Saputra, Fegie Yoanti Wattimena, Davy Jonathan — Tue, 01 Apr 2025 00:00:00 +0700

This study designs and tests a network security system based on a combined Convolutional Neural Network (CNN) and Recurrent Neural Network (RNN) framework. In this study, distributed processing and reinforcement learning methods in combination with differential privacy are introduced into the proposed system to enhance attack detection and network management. The evaluation results show significant improvements; 97.3% detection accuracy, 34% more efficient bandwidth utilization and 45% less latency than the previous system. The 16-node linear scalability of the distributed architecture has a throughput of 1.2 million packets per second. It is defended against adversarial attacks by maintaining accuracy above 92% and provides a total energy saving of 38% using dynamic batch processing. Three months of testing in an operational environment detected 99.2% of 1,247 threats, including 23 new attack types, with an average detection time of 1.8 seconds. Sensitivity analysis was performed to preserve the privacy of sensitive data while maintaining network performance. The results show that the hybrid solution is reliable, scalable and secure for today's network management.

Designing an Early Detection System for Agricultural Land to Reduce the Risk of Crop Failure Based on Information Technology

Tue, 01 Apr 2025 00:00:00 +0700

Crop failures in Indonesia still occur frequently and become a source of problems due to the reduction of food supplies for the community. One of the causes of crop failure is the decline in soil quality due to nutrient content, which is rarely detected by farmers. However, the land quality analysis process that has been carried out so far still tends to take a long time and incur high costs. Therefore, it is necessary to create technology that is expected to be able to detect land quality directly, quickly, and easily. PKM- KC Soil Nutrient Monitoring is designed by creating hardware that can analyze moisture, pH, temperature, and essential macro nutrients, namely nitrogen, phosphorus, and potassium. Additionally, software that can process data and produce results in the form of land quality, land improvement recommendations, and suggested crop commodities. This Soil Nutrient Monitoring tool has been tested and calibrated with an accuracy level of 95%. This tool successfully processes data from hardware in the form of temperature, pH, humidity, and NPK sent via a Bluetooth Low Energy network to software that produces outputs in the form of land quality, land improvement recommendations, and suggested crop commodities

Adopting SOLID Principles in Android Application Development: A Case Study and Best Practices

Nimisha Hake, Laxmipriya Heena Dip — Tue, 01 Apr 2025 00:00:00 +0700

Developing and maintaining large-scale applications has become a daunting task with the rapid evolution of the Android ecosystem. This research examines the application of SOLID (Single Responsibility, Open/Closed, Liskov Substitution, Interface Segregation, and Dependency Inversion) principles in contemporary Android development. By the case study of Meta and an analysis of the application in top tech companies, the present research shares how SOLID principles can achieve better product quality, maintainability, and a positive outcome between your team. The study is based on a mixed-methodology, including qualitative and quantitative, analyzing the source code of 25 enterprise-grade Android applications, in-depth interviews with 50 senior professionals from top-tier technology companies, and code-metrics data for 24 months. We implemented it in Kotlin, taking advantage of the modern Android Jetpack ecosystem. The results of the study demonstrate dramatic increases in all aspects of software development. These include 45% reduction in technical debt, 89% increase in test coverage and 30% reduction in bug rate. A qualitative analysis indicates that teams report increased ease of code maintenance and ramp up of new team members. The research also highlights some of the barriers to applying SOLID: high learning curve, challenges convincing team members to adopt SOLID mindset. Our research contributes (1) a SOLID implementation framework for Android, empirically validated in four case studies. It also includes (2) metrics and tools for measuring adherence to SOLID principles, and (3) recommendations for resolving issues encountered during the implementation of these principles. These results have significant practical implications for mobile software industry practitioners and researchers

Development of Applications with Artificial Intelligence: Expert Perspectives and Recommendations

Julien Florkin — Tue, 01 Apr 2025 00:00:00 +0700

Artificial intelligence (AI) applications are accelerating significantly, supported by three pillars: core technologies, cost efficiency, and strategic direction. A comparative analysis reveals critical contributions from three technologies: (1) Machine Learning (ML) enhances user engagement by 35% through personalized recommendation systems on e-commerce platforms; (2) Natural Language Processing (NLP) reduces customer service operational costs by 47% via intelligent chatbots in the banking sector; and (3) predictive analytics improves cardiovascular disease diagnosis accuracy by 27% based on multicenter clinical data. Estimated AI application development costs range from $50,000 to $250,000, depending on algorithm complexity and computational infrastructure requirements. Future AI development will be shaped by two trends: (1) Edge AI, which reduces data processing latency by 60% through local computation, and (2) Explainable AI (XAI), which enhances algorithm transparency to comply with GDPR and ISO/IEC 23894 regulations. The study underscores that successful AI implementation requires multidisciplinary integration among data scientists, software engineers, and business stakeholders. Strategic recommendations include allocating 15–20% of R&D budgets for continuous learning, establishing an AI ethics committee aligned with OECD principles, and adopting an agile development model for market responsiveness